pyproject.toml

Rama main · réplica de lectura del repositorio original.

[project]
name = "pyrecrawl"
version = "0.8.1"
description = "Web browsing superpowers for AI agents: one MCP tool to scrape, extract, crawl, map, and search any site — self-hosted, no API keys, with a smart auto-fallback ladder."
readme = "README.md"
license = { text = "MIT" }
authors = [
    { name = "Alexander Jay" },
]
keywords = ["mcp", "scraping", "crawl4ai", "scrapling", "firecrawl-alternative", "llm", "rag", "ai-agent", "web-scraping", "ai-agent-tools"]
requires-python = ">=3.10"
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Internet :: WWW/HTTP :: Indexing/Search",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Topic :: Text Processing :: Markup :: Markdown",
]
dependencies = [
    "crawl4ai>=0.9.0",
    "scrapling[fetchers]>=0.4.0",
    "mcp>=1.0,<2.0",
    "pydantic>=2.0",
]

[project.optional-dependencies]
dev = [
    "pytest>=8.0",
    "pytest-asyncio>=0.23",
]
browsers = [
    "playwright>=1.40",
]
docs = [
    "pypdf>=5.0",
    "python-docx>=1.1",
    "python-pptx>=1.0",
]

[project.scripts]
pyrecrawl = "pyrecrawl.cli:main"

[project.urls]
Homepage = "https://github.com/SanggonBoy/PyreCrawl"
Repository = "https://github.com/SanggonBoy/PyreCrawl"
Documentation = "https://github.com/SanggonBoy/PyreCrawl#readme"
Issues = "https://github.com/SanggonBoy/PyreCrawl/issues"
Changelog = "https://github.com/SanggonBoy/PyreCrawl/releases"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["src/pyrecrawl"]

[tool.pytest.ini_options]
asyncio_mode = "auto"
# no tests/ dir yet — executable checks live in scripts/selfcheck.py + scripts/probe_stdio.py